Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases expressing confusion or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ollectionView
    -0.51
    Filmographie
    -0.47
     époque
    -0.46
     aina
    -0.46
     חיצוניים
    -0.45
    Espèce
    -0.45
    WriteTagHelper
    -0.44
    Parcelize
    -0.43
    archical
    -0.43
     frappe
    -0.43
    POSITIVE LOGITS
    LEncoder
    0.71
    polazione
    0.69
     your
    0.65
    your
    0.64
     незавершена
    0.63
    setupUi
    0.61
    YOUR
    0.59
     Your
    0.58
     yourself
    0.57
     للاسماء
    0.57
    Act Density 0.339%

    No Known Activations